© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15837
    Prev
    Next
    INDEX
    Explanations

    adjectives with comparative or superlative forms, sometimes near the word "not"

    oai_token-act-pair · gemini-2.0-flash

    most/more

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.66
    rrggbb
    -0.55
    HtmlAttribute
    -0.55
    lysm
    -0.52
    lessness
    -0.52
    WebServlet
    -0.52
    formKey
    -0.51
    inescence
    -0.51
    CodedInputStream
    -0.50
    atoshi
    -0.49
    POSITIVE LOGITS
    NameInMap
    0.69
     EconPapers
    0.60
    
    0.58
     Audiodateien
    0.57
    ///</
    0.57
    Datuak
    0.55
     gynhyrchwyd
    0.54
    PreferredItem
    0.53
     fær
    0.52
     scolaires
    0.52
    Activations Density 8.415%

    No Known Activations